Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/StarTrail-org/PixelRAG
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/StarTrail-org/PixelRAG.md
Description: hello-agents and PixelRAG share 19 technologies: FastAPI, OpenAI, Hugging Face, React, fastmcp, AIOHTTP, accelerate, MCP, peft, safetensors, torch, transformers, tiktoken, datasets, lxml, pillow, beautifulsoup4, Tailwind CSS, and react-markdown. Both are written in Python.

# hello-agents vs PixelRAG

hello-agents and PixelRAG share 19 technologies: FastAPI, OpenAI, Hugging Face, React, fastmcp, AIOHTTP, accelerate, MCP, peft, safetensors, torch, transformers, tiktoken, datasets, lxml, pillow, beautifulsoup4, Tailwind CSS, and react-markdown. Both are written in Python.

- [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents): 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
- [StarTrail-org/PixelRAG](https://seerepo.com/r/StarTrail-org/PixelRAG): https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

## What they share and what sets them apart

- In common: FastAPI, OpenAI, Hugging Face, React, fastmcp, AIOHTTP, accelerate, MCP, peft, safetensors, torch, transformers, tiktoken, datasets, lxml, pillow, beautifulsoup4, Tailwind CSS, react-markdown
- Only in hello-agents: uvicorn, aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, libsql-client, oracledb, pymilvus, Qdrant, Flask, python, react-dom, starlette, anyio, Streamlit, Vite, Vue, vue-router, react-router-dom, cycler, fonttools, soupsieve, contourpy, ipywidgets, Plotly, Gradio, matplotlib, Rich, seaborn, alembic, SQLAlchemy, python-jose, passlib, bcrypt, bitsandbytes, camel-ai, mermaid, onnxruntime, tavily-python, textblob, tokenizers, hello-agents, agentscope, scikit-learn, sentence-transformers, autogen-agentchat, autogen-ext, langchain-openai, langdetect, LangGraph, paddlenlp, rank-bm25, spaCy, imaplib2, markdown, openpyxl, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, feedparser, pymupdf, pypdf2, jinja2, pymupdf4llm, annotated-types, email-validator, Pydantic, jsonschema, kubernetes, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, loguru, ant-design-vue, D3, @ant-design/icons-vue, katex, markdown-it, vue-flow, @monaco-editor/loader, Chart.js, vue-chartjs, highlight.js, dompurify, marked, Element, vue-echarts, echarts, @element-plus/icons-vue, Leaflet, @amap/amap-jsapi-loader, html2canvas, jspdf
- Only in PixelRAG: Next.js, Anthropic, litellm, nvidia-cudnn-cu12, torchvision, faiss-cpu, qwen-vl-utils, vLLM, botocore, @opencode-ai/plugin, class-variance-authority, next-themes, tailwind-merge, Base UI, Framer, Lucide, remark-gfm, Zod

## Side by side

| | hello-agents | PixelRAG |
|---|---|---|
| Size | 227,369 lines written, 1,215 code files | 59,214 lines written, 141 code files |
| Who writes it | 3.3% of its commits signed by AI. With Codex, Claude Code, and Cursor | 24.1% of its commits signed by AI. With Claude Code |
| Activity | Last push November 11, 2026, 667 commits, 86,829 stars | Last push November 11, 2026, 133 commits, 10,914 stars |
| Tests | 103 test files. 6.8% of its code files have a test that imports them | 45 test files. 16.3% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, hello-agents or PixelRAG?

hello-agents, with 227,369 lines written; PixelRAG has 59,214.

The proof: [datawhalechina/hello-agents's code at commit 2a506bc](https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)

### Which has more GitHub stars, hello-agents or PixelRAG?

hello-agents, with 86,829 stars; PixelRAG has 10,914.

The proof: [datawhalechina/hello-agents on GitHub](https://github.com/datawhalechina/hello-agents)

### Which has more tests, hello-agents or PixelRAG?

hello-agents, with 103 test files; PixelRAG has 45.

The proof: [datawhalechina/hello-agents's code at commit 2a506bc](https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)

### Which was updated more recently, hello-agents or PixelRAG?

Both got their last push on November 11, 2026.

The proof: [datawhalechina/hello-agents's commits on GitHub](https://github.com/datawhalechina/hello-agents/commits)

### Which has more commits signed by AI, hello-agents or PixelRAG?

PixelRAG: an AI signed 24.1% of its commits, with Claude Code; in hello-agents, 3.3%.

The proof: [the commits each tool signed in StarTrail-org/PixelRAG](https://seerepo.com/r/StarTrail-org/PixelRAG/ai)

## Sources

- datawhalechina/hello-agents: Read on November 12, 2026, at commit 2a506bc (https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)
- StarTrail-org/PixelRAG: Read on November 13, 2026, at commit 16f35e5 (https://github.com/StarTrail-org/PixelRAG/tree/16f35e58dc7fec80e482638cdf4ab8ec8347912c)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.